Modeling Review Spam Using Temporal Patterns and Co-bursting Behaviors

Abstract

Online reviews play a crucial role in helping consumers evaluate and compare products and services. However, review hosting sites are often targeted by opinion spamming. In recent years, many such sites have put a great deal of effort in building effective review filtering systems to detect fake reviews and to block malicious accounts. Thus, fraudsters or spammers now turn to compromise, purchase or even raise reputable accounts to write fake reviews. Based on the analysis of a real-life dataset from a review hosting site (dianping.com), we discovered that reviewers' posting rates are bimodal and the transitions between different states can be utilized to differentiate spammers from genuine reviewers. Inspired by these findings, we propose a two-mode Labeled Hidden Markov Model to detect spammers. Experimental results show that our model significantly outperforms supervised learning using linguistic and behavioral features in identifying spammers. Furthermore, we found that when a product has a burst of reviews, many spammers are likely to be actively involved in writing reviews to the product as well as to many other products. We then propose a novel co-bursting network for detecting spammer groups. The co-bursting network enables us to produce more accurate spammer groups than the current state-of-the-art reviewer-product (co-reviewing) network.